mail_stats

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare readOnlyHint/destructiveHint, and the description adds genuinely new behavioral facts: it reads the Envelope Index only and never launches Mail, it counts DISTINCT messages (raw rows overcount up to 3.6x), and output is deliberately token-bounded with top-N instead of per-day series. The trailing 'Read-only.' merely repeats the annotation, but the surrounding disclosures are substantive.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loaded with the one-line purpose, then progressively adds constraints and output shape; the deduplication warning and the account-UUID caveat each earn their space. The enumerated return-key list is somewhat verbose given an output schema exists, though it doubles as guidance on what is and isn't included (top-N, no per-day series).

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a two-parameter read-only aggregate with an output schema and clear annotations, nothing material is missing: prerequisite access, counting semantics, parameter format, output shape and the follow-up call to resolve account UUIDs are all covered. An agent could call this correctly without inspecting anything else.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description carries the burden and largely does: `days` is defined as the lookback window, and `account` is explicitly described as a raw account UUID — the same UUID carried by mail Pointer and mail_overview rows — not a display name. That is exactly the disambiguation an agent needs; only the default values/edge behavior are left to the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific resource and metric set ('Mail volume, read ratio and top senders over the last `days`') and frames the scope as an aggregate over the whole store, which cleanly separates it from per-message siblings like mail_search and mail_thread. The parenthetical '(Full Disk Access)' and the 'never launches Mail' clause further pin down what kind of tool this is.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear trigger context (summary statistics over a day window rather than message listing) and an explicit follow-up path: 'map the uuid to a name with one `mail_overview` call.' It also states the Full Disk Access prerequisite. It stops short of naming an explicit alternative tool and when-not-to-use condition, so it is strong but not complete routing guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.